Browse > Article
http://dx.doi.org/10.12673/jant.2022.26.6.528

A Study on Auto-Classification of Aviation Safety Data using NLP Algorithm  

Sung-Hoon Yang (Data Analysis & research Center, Korea Institute of Aviation Safety Technology)
Young Choi (Data Analysis & research Center, Korea Institute of Aviation Safety Technology)
So-young Jung (Data Analysis & research Center, Korea Institute of Aviation Safety Technology)
Joo-hyun Ahn (Data Analysis & research Center, Korea Institute of Aviation Safety Technology)
Publication Information
Journal of Advanced Navigation Technology / v.26, no.6, 2022 , pp. 528-535 More about this Journal
Abstract
Although the domestic aviation industry has made rapid progress with the development of aircraft manufacturing and transportation technologies, aviation safety accidents continue to occur. The supervisory agency classifies hazards and risks based on risk-based aviation safety data, identifies safety trends for each air transportation operator, and conducts pre-inspections to prevent event and accidents. However, the human classification of data described in natural language format results in different results depending on knowledge, experience, and propensity, and it takes a considerable amount of time to understand and classify the meaning of the content. Therefore, in this journal, the fine-tuned KoBERT model was machine-learned over 5,000 data to predict the classification value of new data, showing 79.2% accuracy. In addition, some of the same result prediction and failed data for similar events were errors caused by human.
Keywords
Auto-Classification; Aviation Safety Data; Aviation Safety Inspector; KoBERT; NLP;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 MOLIT(Ministry of Land, Infrastructure and Transport), The Aviation Safety White Book, pp. 29-35, 2022.
2 E. J. Kim, "Study of the Introduction on the Aviation Safety Data Protection System," The Korean Journal of Air & Space Law and Policy, Vol. 33, No. 1, pp. 81-120, 2018.   DOI
3 Ministry of Land, Transport & Maritime Affairs Republick of Korea. Aviation Safety Inspector Manual. Korean Law Information Center [Internet]. Available: https://law.go.kr/LSW/admRulLsInfoP.do?chrClsCd=&adm RulSeq=2100000212305.
4 KIAST(Korea Institute of Aviation Safety Technology) : Final Report on the Development of System-based Aviaion Safety Oversight Support Technology, MOLIT, Technical Report OTKCRK210001, 2020.
5 C. S. Lee, Z. M. Paing, H. M. Yeo, D.S. Kim, and H.J. Baik, "Development of a Prediction Model and Correlation Analysis of Weather-induced Flight Delay at Jeju International Airport Using Machine Learning Technique," Journal of the Korean Society for Aeronautical and Flight Operation, Vol. 29, No. 4, 2021, pp. 1-20.   DOI
6 A. Agarwal, R. Gite, S. Laddha, P. Bhattacharyya, S. Kar, A. Ekbal, P. Thind, R. Zele, and R. Shankar, "Knowledge Graph - Deep Learning: A Case Study in Question Answering in Aviation Safety Domain," in Proceeding of the LREC 2022 : 14th Conference on Language Resources and Evaluation, Marseille, arXiv:2205.15952 [cs.CL], 2022.
7 W. Zhang, H. Shi, Y. Yang, and Y. Luo, "Research on the Classification of Aviation Safety Reports Based on Text and Knowledge Graph," Journal of Physics: Conference Series, Vol. 1646, No. 1, 2020. pp. 1-6.   DOI
8 K. H. Kim, Natural Language Processing with PyTorch, Hanbitmedia, p.520, 2019.
9 H. Sak, A. Senior, and F. Beaufays, "Long short-term memory recurrent neural network architectures for large scale acoustic modeling," in Proceeding of the 15th Annual Conference of the International Speech Communication Association on Computer Science, Singapore, pp. 338-342, 2014.
10 Colah's blog. Understanding LSTM Networks [Internet]. Available: http://colah.github.io/posts/2015-08-Understanding-LSTMs/
11 S. H. Hwang, D. H. Kim, "BERT-based Classification Model for Korean Documents," The Journal of Society for e-Business Studies Vol. 25, No. 1, 2020, pp. 203-214.
12 J. H. Lee, The review of Deep learning, Master's Thesis, Ewha Womans University, Korea, Dec. 2018.
13 M. E. Peters, M. Neumann., M. Iyyer, M. Gardner, C. Clark, K. Lee, and L. Zettlemoyer, "Deep Contextualized Word Representations," in Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Louisiana, pp. 2227-2237, Mar. 2018.
14 J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, "BERT:Pre-traning of Deep Bidirectional Transformers for Language Understanding," in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minnesota, pp. 4171-4186, May. 2019.
15 J. Y. Choi, H. S. Lim,"E-commerce data based Sentiment Analysis Model Implementation using Natural Language Processing Model," Journal of the Korea Convergence Society, Vol. 11., No. 11, 2020, pp. 33-39.
16 H. R. Cho, H. Y. Im, J. W. Cha, and Y. M. Yi, "Automatic Score Range Classification of Korean Essays Using Deep Learning-based Korean Language Models - The Case of KoBERT & KoGPT2," Journal of the International Network for Korean Language and Culture, Vol. 18, No. 1, 2021, pp. 217-241.    DOI